Environment Sensing Intelligent Apparatus

1. A system comprising: an audio playback device configured to drive an audio reproduction device at a volume level; an audio capture device configured to convert sound waves into an audio input; and an environment sensing device configured to detect, based on the audio input, environmental conditions surrounding a user of the audio playback device, the environmental conditions including a loudness estimation indicative of a level of background noise included in the audio input and an audio content classification indicative of a presence of speech in the audio input, determine, according to the environmental conditions, a playback action to alter the volume level being provided by the audio playback device, and provide, to the audio playback device, an adjustment to the volume level in accordance with the playback action.

2. The system of claim 1 , wherein the environment sensing device is further configured to determine the playback action according to a mapping of environmental conditions to playback actions, wherein the mapping specifies to lower the volume level when: (i) the audio content classification indicates the presence of speech and the loudness estimation indicates a loudness condition below a predefined sound pressure level, or (ii) the audio content classification indicates a presence of background noise and the loudness estimation indicates a loudness condition above the predefined sound pressure level.

3. The system of claim 1 , wherein the audio capture device is integrated into one of: (i) the audio playback device, or (ii) the audio reproduction device.

4. The system of claim 1 , wherein the environment sensing device is further configured to: determine an average absolute amplitude of the audio input; identify a sound pressure level according to the average absolute amplitude according to a sound-input-level characterization of the audio capture device; count a number of samples of the audio input that exceed a pre-determined loudness threshold over a predetermined period of time; and determine that the loudness estimation corresponds to one of (i) a high loudness condition when the count exceeds a threshold value, (ii) a low loudness condition when the count does not exceed the threshold value, and (iii) a silence condition when the audio input includes substantially no sound information.

5. The system of claim 1 , wherein the environment sensing device is further configured to: pass the audio input through a band pass filter to select for first formants of speech; estimate a pitch of the audio input; count a number of samples of the audio input in which the pitch is within a range for a first formant of speech over a predetermined period of time; and determine that the audio content classification corresponds to one of (i) a speech and noise condition when the count exceeds a first threshold value, (ii) a speech condition when the count exceeds a second threshold value but does not exceed the first threshold value, and (iii) a noise condition when the count does not exceeds the second threshold value.

6. The system of claim 5 , wherein the environment sensing device is further configured to estimate the pitch using an average magnitude difference function (AMDF), the first threshold value is approximately 65% of the samples, and the second threshold value is approximately 40% of the samples.

7. The system of claim 1 , wherein the environment sensing device is further configured to: perform recognition of the speech on the audio input; compare the recognized speech with user-customizable text; and mute the volume level when a match is detected of the recognized speech with the user-customizable text.

8. The system of claim 7 , wherein the environment sensing device is further configured to, when the environment sensing device is moving, further determine (i) a first speed changing position in which the environment sensing device is moving at a rate indicative of travel without a vehicle, and (ii) a second speed changing position in which the device is moving at a speed indicative of travel within the vehicle.

9. The system of claim 1 , wherein the environment sensing device is further configured to: receive accelerometer positional data; determine, based on the accelerometer position data, a position change of one of: (i) a static position in which the environment sensing device is not moving, and (ii) a changing position in which the environment sensing device is moving; and determine the playback action to be performed further according to a determined position change estimation of the enviroment sensing device.

10. The system of claim 1 , further comprising a pressure sensor, wherein the environment sensing device is further configured to mute the volume level when the pressure sensor indicates a change in movement.

11. A method comprising: detecting, based on audio input from an audio capture device, environmental conditions surrounding a user of an audio playback device driving an audio reproduction device at a volume level, the environmental conditions including a loudness estimation indicative of a level of background noise included in the audio input and an audio content classification indicative of presence of speech in the audio input; determining, according to the environmental conditions, a playback action to alter the volume level being provided by the audio playback device; and providing, to the audio playback device, an adjustment to the volume level according to the playback action.

12. The method of claim 11 , further comprising determining the playback action according to a mapping of environmental conditions to playback actions, wherein the mapping specifies to lower the volume level when: (i) the audio content classification indicates the presence of speech and the loudness estimation indicates a loudness condition below a predefined sound pressure level, or (ii) the audio content classification indicates a presence of noise and the loudness estimation indicates a loudness condition above the predefined sound pressure level.

13. The method of claim 11 , further comprising: determining an average absolute amplitude of the audio input; identifying a sound pressure level according to the average absolute amplitude according to a sound-input-level characterization of the audio capture device; counting a number samples of the audio input that exceed a pre-determined loudness threshold over a predetermined period of time; and determining that the loudness estimation corresponds to one of (i) a high loudness condition when the count exceeds a threshold value, (ii) a low loudness condition when the count does not exceed the threshold value, and (iii) a silence condition when the audio input includes substantially no sound information.

14. The method of claim 11 , further comprising: passing the audio input through a band pass filter to select for first formants of speech; estimating a pitch of the audio input; counting a number of samples of the audio input in which the pitch is within a range for a first formant of speech over a predetermined period of time; and determining that the audio content classification corresponds to one of (i) a speech and noise condition when the count exceeds a first threshold value, (ii) a speech condition when the count exceeds a second threshold value but does not exceed the first threshold value, and (iii) a noise condition when the count does not exceeds the second threshold value.

15. The method of claim 11 , further comprising one or more of: performing recognition of the speech on the audio input, comparing the recognized speech with the user-customizable text, and muting the volume level when a match is detected of the recognized speech with the user-customizable text; and muting the volume level when data received from a presure sensor indicates a change in movement of the audio playback device.

16. A non-transitory computer-readable medium comprising computer instructions that, when executed by a processor of an audio playback device, cause the audio playback device to perform operations including to: detect, based on audio input from an audio capture device, environmental conditions surrounding a user of an audio playback device driving an audio reproduction device at a volume level, the environmental conditions including a loudness estimation indicative of a level of background noise included in the audio input and an audio content classification indicative of presence of speech in the audio input; determine, according to the environmental conditions, a playback action to alter the volume level being provided by the audio playback device; and provide an adjustment to the volume level in accordance with the playback action.

17. The medium of claim 16 , further comprising instructions configured to cause the audio playback device to determine the playback action according to a mapping of environmental conditions to playback actions, wherein the mapping specifies to lower the volume level when: (i) the audio content classification indicates the presence of speech and the loudness estimation indicates a loudness condition below a predefined sound pressure level, or (ii) the audio content classification indicates a presence of noise and the loudness estimation indicates a loudness condition above the predefined sound pressure level.

18. The medium of claim 16 , further comprising instructions configured to cause the audio playback device to: determine an average absolute amplitude of the audio input; identify a sound pressure level according to the average absolute amplitude according to a sound-input-level characterization of the audio capture device; count a number of samples of the audio input that exceed a pre-determined loudness threshold over a predetermined period of time; and determine that the loudness estimation corresponds to one of (i) a high loudness condition when the count exceeds a threshold value, (ii) a low loudness condition when the count does not exceed the threshold value, and (iii) a silence condition when the audio input includes substantially no sound information.

19. The medium of claim 16 , further comprising instructions configured to cause the audio playback device to: pass the audio input through a band pass filter to select for first formants of speech; estimate a pitch of the audio input; count a number of samples of the audio input in which the pitch is within a range for a first formant of speech over a predetermined period of time; and determine that the audio content classification corresponds to one of (i) a speech and noise condition when the count exceeds a first threshold value, (ii) a speech condition when the count exceeds a second threshold value but does not exceed the first threshold value, and (iii) a noise condition when the count does not exceeds the second threshold value.

20. The medium of claim 16 , further comprising instructions configured to cause the audio playback device to one or more of: perform recognition of the speech on the audio input, compare the recognized speech with user-customizable text, and mute the volume level when a match is detected of the recognized speech with the user-customizable text; and mute the volume level when data received from a pressure sensor indicates a change in movement of the audio playback device.